Pedestrian re -identification method based on dual -binding degree learning and sample reinstation

Abstract

The invention discloses a pedestrian re-identification method based on double-constraint metric learning and sample reordering, which includes two stages of training and testing; the training stage includes the following steps: establishing cross-camera association constraints; establishing same-camera association constraints; measuring Matrix solution; the test stage includes the following steps: using the metric matrix to project the feature space; calculating the Euclidean distance between the query picture and the candidate picture in the feature space; calculating the initial ordering of the candidate pictures; selecting the first K candidate pictures in the sorting queue; using The relevance of the first K candidate images in the feature space constructs a probabilistic hypergraph; calculates the reordering result based on the probabilistic hypergraph; returns the final ranking of candidate images. The present invention considers two kinds of association constraints of training samples at the same time, so that the learned feature space is more suitable for pedestrian re-identification, and at the same time uses the relevance of candidate pictures to reorder to obtain more accurate pedestrian re-identification results.

Description

technical field [0001] The invention relates to a method in the technical field of video image processing, in particular to a pedestrian re-identification method based on double-constraint metric learning and sample reordering. Background technique [0002] Video surveillance provides a rich source of information for security early warning, investigation and evidence collection, and suspect tracking. However, the monitoring range of a single camera is very limited, so larger or more complex scenes (such as railway stations, airports, campuses, etc.) cannot be monitored in all directions. In order to capture more comprehensive and extensive information in public areas, a large number of surveillance cameras are usually required to work together. Traditional video processing technology is mainly designed for a single camera. When a pedestrian target moves out of the current video, it is impossible to judge the target's whereabouts. Therefore, how to re-identify pedestrians i...

AI Technical Summary

Problems solved by technology

However, the existing metric learning algorithms only consider the cross-camera correlation information between pedestrian images under different cameras during the training process, while ignoring the correlation between different pedestrian images within the same camera.

At the same time, the metric learning algorithm is prone to overfitting on the training set, and in the test phase, relying entirely on the learned distance metric matrix for similarity ranking may result in suboptimal pedestrian re-identification results.

Images